CN112182017A - Method for optimizing data exploration based on user interaction process - Google Patents
Method for optimizing data exploration based on user interaction process Download PDFInfo
- Publication number
- CN112182017A CN112182017A CN202011065504.3A CN202011065504A CN112182017A CN 112182017 A CN112182017 A CN 112182017A CN 202011065504 A CN202011065504 A CN 202011065504A CN 112182017 A CN112182017 A CN 112182017A
- Authority
- CN
- China
- Prior art keywords
- interaction
- view
- path
- user
- frequent item
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2423—Interactive query statement specification based on a database schema
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Fuzzy Systems (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for optimizing data exploration based on a user interaction process, which comprises the steps of collecting and analyzing interaction data generated by a user during data exploration, firstly, defining a view of user interaction as a view I, defining and recording an analysis view as a view II, defining the interaction of the user, judging whether required information is obtained from the view I or not, meeting conditions and finishing the interaction; otherwise, carrying out interaction, and sequentially compressing and grouping the interaction paths; then, excavating a frequent item set in the group through an FP-Growth algorithm; calculating a key interaction path, namely a shortest interaction path, by adopting an optimized Dijkstra algorithm; finally, respectively labeling the frequent item with the highest confidence level in the frequent item set and the key interaction path to a view II, and completing interaction if required information is obtained from the view I; otherwise, continuing the interaction until the condition is met. The invention can help the user to better observe the self-interaction process through the second view, thereby better exploring data.
Description
Technical Field
The invention relates to a method for optimizing data exploration steps, and belongs to a research problem in the field of data exploration. The method optimizes data exploration steps by collecting and analyzing data exploration interactive processes of users.
Background
With the development of scientific technology, the generation of information is explosively increased, and immeasurable data can be generated every day. With the increasingly simple acquisition of data and the continuous enhancement of computer computing power, a plurality of excellent data mining methods appear, but the problem of insufficient intelligent degree still exists at present, and people's analysis and decision are required to be added in the data analysis process.
Data exploration refers to the visualization of an unknown structured data set through an interactive view, so that useful information can be visually discovered from the view through interaction. Analysts typically begin with a broad concept, familiarizing step by step with the structure of the data, focusing their attention on different interesting parts many times, and attempting to discover useful information.
However, during data exploration, a data analyst, when discovering an analysis state of interest, may not be able to determine whether continuing the analysis from that state yields useful results. Or when the useful information is discovered, the result is not known through which interaction process, and the effective interaction process in the analysis of the data set cannot be summarized.
Therefore, there is a need for a more flexible method of responding according to user interaction processes to help optimize the interaction steps in data exploration.
In the current study, the user's interaction behavior is first defined. Because the interaction behaviors are multiple and diverse, for various interactive modes, the interactive modes need to be classified according to the characteristics of the interactive modes, for example, the interactive modes are reduced, enlarged and translated to be regarded as filtering operation; single selection, box selection, etc. can all be considered selection operations. In the actual process of user interaction, many redundant operations are likely to be generated, for example, when translation interaction is performed, it is often difficult for a user to adjust the view to a satisfactory position at one time, so that continuous same interaction can be generated in a short time, and the difference of the view data states generated by each interaction is small, so the operations can be removed; and by generating the key path in real time, an analyst can better master the analysis process.
Disclosure of Invention
Aiming at the prior art, the invention provides a method for optimizing data exploration based on a user interaction process, wherein recording and analysis of the user interaction process are considered, so that the step of optimizing data exploration is realized.
In order to solve the technical problems, the invention provides a method for optimizing data exploration based on a user interaction process, which mainly collects and analyzes interaction data generated by a user during data exploration, and comprises the following steps: firstly, defining a view interacted by a user as a first view, defining a recording analysis view as a second view, defining the interaction of the user, judging whether required information is obtained from the first view, meeting conditions and finishing the interaction; otherwise, carrying out interaction, and sequentially compressing and grouping the interaction paths; then, excavating a frequent item set in the groups through an FP-Growth algorithm, wherein the length of the frequent item in the frequent item set is 2 to 5; calculating a key interaction path by adopting an optimized Dijkstra algorithm to reduce the complexity of the calculation of the key path, wherein the key interaction path is the shortest interaction path; finally, respectively marking the frequent item with the highest confidence level in the frequent item set and the key interaction path to a view II, judging whether the required information is obtained from the view I, meeting the conditions and finishing the interaction; otherwise, continuing the interaction until the condition is met.
Further, the method for optimizing data exploration according to the present invention is characterized in that: the method comprises the following specific steps:
step one, defining the interaction of a user:
data exploration requires a user to interact with a view, and the view interacted by the user is set as a view I; according to the method, the interactive process of the user is recorded and analyzed according to the interaction of the user, and the interactive process and the analysis result of the user are marked on another view, so that the user is helped to complete the interaction better, and the view is set as a view II;
N＝{N1，N2，...，Nnn refers to a data state set of a view I after interaction; wherein N isiRefers to the data state of the view one after the user interacts with the view one time；P＝{P1，P2，...，PnP is an interaction path set, which is a set between data states of adjacent views; wherein, PiMeans NiAnd Ni+1User interaction between;
step two, if the required information is obtained from the view one, the interaction is completed; otherwise, carrying out interaction, and then carrying out the third step;
step three, compressing the interaction path set P and the view data state set N:
by traversing the interaction path set P, if there are consecutive identical Pi，Pi+1，...，Pi+nAnd then compare Pi，Pi+1，...，Pi+nView data state N in betweeni+1，Ni+2，...，Ni+n-1View data state NiFor multidimensional data nodes, the similarity comparison is carried out by calculating the Manhattan distance:
wherein, distman(Ni，Ni+1) Represents NiAnd Ni+1The Manhattan distance between, k represents NiHaving k dimensions, NijRepresents NiThe jth dimension of (a); setting a threshold value c-k 0.15 when distman(Ni，Ni+1) C is less than or equal to c, the interaction path Pi+1And view data state Ni+1Is compressed;
step four, grouping of the interaction path sets:
according to PiAnd Pi+1The time interval t between the two groups the interaction path set P, when t < 5s, PiAnd Pi+1Belong to the same group, otherwise Pi+1New packets are formed, thereby obtaining a set of packets G ═ G of interaction paths1，G2，...，GnIn which GiRefers to a group of interaction paths;
step five, mining the frequent item set of the interaction path:
excavating a frequent item set in the group set G of the interactive paths obtained in the step four by adopting an FP-Growth algorithm, wherein the method comprises the following steps: let the number of groups in the interactive path grouping set G be n, and the minimum support degree min of the frequent item setsupportP is equal to p × n, the value range of p is 0.2-0.5, and the length of the frequent item in the frequent item set is 2-5;
step six, extracting a key interaction path:
calculating a key interaction path in the interaction path set according to the interaction path set compressed in the step three by adopting an optimized Dijkstra algorithm, wherein the method comprises the following steps of:
first, an initial starting point is designated as an initial interactive view data state N1Setting two sets S and U, wherein the set S is used for recording the interactive view data state nodes with the shortest paths already obtained, and the U is used for recording the nodes except the nodes in the set S;
then, calculating the current key interaction path PkeycurrThere are two cases according to the difference of the operation:
case one, the interaction is a direct operation on view one, resulting in a new interaction path PiAnd a new interactive view data state NiNew interaction path PiFrom the current interaction view data state Ni-1Pointing to a new Interactive View data State NiNew interactive view data state NiAdded to the set U, node NiTo the initial node N1Is the node Ni-1To the initial node N1Plus 1, the distance of (c); from the initial node N1To node NiThe inter-interaction path is a key interaction path;
case two, the interaction is a jump operation between view data states, resulting in a new interaction path PiSearching the shortest distance corresponding to the node after the jump in the set S, wherein the interaction path corresponding to the shortest distance is the key interaction path;
step seven, marking prompt information on the view two:
and respectively labeling the frequent item with the highest confidence level in the frequent item set obtained in the fifth step and the key interaction path obtained in the sixth step on the second view, and returning to the second step.
And in the seventh step, marking the prompt message by using d3 js.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method for optimizing data exploration based on a user interaction process, which considers the recording and analysis of the user interaction process more than the previous methods. According to the invention, the user interaction process is recorded and analyzed, and a method of mining frequent item sets and extracting key interaction paths is adopted and then marked on the second view, so that the user is helped to better observe the self interaction process through the second view, and the data exploration is better carried out.
Drawings
FIG. 1 is a flow chart of a method for optimizing data exploration according to the present invention.
Detailed Description
The technical solutions of the present invention are further described in detail with reference to the accompanying drawings and specific embodiments, which are only illustrative of the present invention and are not intended to limit the present invention.
The invention discloses a method for optimizing data exploration based on a user interaction process, which is mainly used for optimizing the data exploration by collecting and analyzing interaction data generated by a user during the data exploration, and as shown in figure 1, the method mainly comprises the following steps: firstly, defining a view interacted by a user as a first view, defining a recording analysis view as a second view, defining the interaction of the user, judging whether required information is obtained from the first view, meeting conditions and finishing the interaction; otherwise, carrying out interaction, and sequentially compressing and grouping the interaction paths; then, excavating a frequent item set in the groups through an FP-Growth algorithm, wherein the length of the frequent item in the frequent item set is 2 to 5; calculating a key interaction path by adopting an optimized Dijkstra algorithm to reduce the complexity of the calculation of the key path, wherein the key interaction path is the shortest interaction path; finally, respectively marking the frequent item with the highest confidence level in the frequent item set and the key interaction path to a view II, judging whether the required information is obtained from the view I, meeting the conditions and finishing the interaction; otherwise, continuing the interaction until the condition is met. The method comprises the following specific steps:
step one, defining the interaction of a user:
data exploration requires a user to interact with a view, and the view interacted by the user is set as a view I; according to the method, the interactive process of the user is recorded and analyzed according to the interaction of the user, and the interactive process and the analysis result of the user are marked on another view, so that the user is helped to complete the interaction better, and the view is set as a view II;
N＝{N1，N2，...，Nnn refers to a data state set of a view I after interaction; wherein N isiThe method is characterized in that the data state of a view I is obtained after a user interacts with the view I once; p ═ P1，P2，...，PnP is an interaction path set, which is a set between data states of adjacent views; wherein, PiMeans NiAnd Ni+1User interaction between;
step two, if the required information is obtained from the view one, the interaction is completed; otherwise, carrying out interaction, and then carrying out the third step;
step three, compressing the interaction path set P and the view data state set N:
by traversing the interaction path set P, if there are consecutive identical Pi，Pi+1，...，Pi+nAnd then compare Pi，Pi+1，...，Pi+nView data state N in betweeni+1，Ni+2，...，Ni+n-1View data state NiFor multidimensional data nodes, the similarity comparison is carried out by calculating the Manhattan distance:
wherein, distman(Ni，Ni+1) Represents NiAnd Ni+1The Manhattan distance between, k represents NiHaving k dimensions, NijRepresents NiThe jth dimension of (a); setting a threshold value c-k 0.15 when distman(Ni，Ni+1) C is less than or equal to c, the interaction path Pi+1And view data state Ni+1Is compressed;
for example: the interaction path set P (part) before compression is shown in table 1, and the interaction path set P (part) after compression is shown in table 2.
TABLE 1 interaction Path set before compression P (part)
TABLE 2 set of interaction paths P (partial) after compression
Step four, grouping of the interaction path sets:
according to PiAnd Pi+1The time interval t between the two groups the interaction path set P, when t < 5s, PiAnd Pi+1Belong to the same group, otherwise Pi+1New packets are formed, thereby obtaining a set of packets G ═ G of interaction paths1，G2，...，GnIn which GiRefers to a group of interaction paths;
the packet sets are shown in table 3.
TABLE 3 grouping sets
Step five, mining the frequent item set of the interaction path:
excavating a frequent item set in the group set G of the interactive paths obtained in the step four by adopting an FP-Growth algorithm, wherein the method comprises the following steps: let the number of groups in the interaction path grouping set G be n, theMinimum support min of frequent item setsupportP is equal to p × n, the value range of p is 0.2-0.5, and the length of the frequent item in the frequent item set is 2-5;
step six, extracting a key interaction path:
calculating a key interaction path in the interaction path set according to the interaction path set compressed in the step three by adopting an optimized Dijkstra algorithm, wherein the method comprises the following steps of:
first, an initial starting point is designated as an initial interactive view data state N1Setting two sets S and U, wherein the set S is used for recording the interactive view data state nodes with the shortest paths already obtained, and the U is used for recording the nodes except the nodes in the set S;
then, calculating the current key interaction path PkeycurrThere are two cases according to the difference of the operation:
case one, the interaction is a direct operation on view one, resulting in a new interaction path PiAnd a new interactive view data state NiNew interaction path PiFrom the current interaction view data state Ni-1Pointing to a new Interactive View data State NiNew interactive view data state NiAdded to the set U, node NiTo the initial node N1Is the node Ni-1To the initial node N1Plus 1, the distance of (c); from the initial node N1To node NiThe inter-interaction path is a key interaction path;
case two, the interaction is a jump operation between view data states, resulting in a new interaction path PiSearching the shortest distance corresponding to the node after the jump in the set S, wherein the interaction path corresponding to the shortest distance is the key interaction path;
at present, the key interaction path is drag, zoom, brush, filter, drag.
Step seven, marking prompt information on the view two:
and respectively labeling the frequent item with the highest confidence level in the frequent item set obtained in the fifth step and the key interaction path obtained in the sixth step on the second view, and returning to the second step.
The most frequent items with the highest confidence coefficient are currently brush, filter and drag, and the key interaction path is drag, zoom, brush, filter and drag.
After drawing a normal interaction path at each step, generating corresponding data of the prompt message through the step two, the step four and the step five, and then marking the corresponding prompt message on the interaction view through the d3js library.
While the present invention has been described with reference to the accompanying drawings, the present invention is not limited to the above-described embodiments, which are illustrative only and not restrictive, and various modifications which do not depart from the spirit of the present invention and which are intended to be covered by the claims of the present invention may be made by those skilled in the art.
Claims (3)
1. A method for optimizing data exploration based on a user interaction process is characterized in that: the method mainly comprises the steps of collecting and analyzing interactive data generated by a user during data exploration, and comprises the following steps:
firstly, defining a view interacted by a user as a first view, defining a recording analysis view as a second view, defining the interaction of the user, judging whether required information is obtained from the first view, meeting conditions and finishing the interaction; otherwise, carrying out interaction, and sequentially compressing and grouping the interaction paths; then, excavating a frequent item set in the groups through an FP-Growth algorithm, wherein the length of the frequent item in the frequent item set is 2 to 5; calculating a key interaction path by adopting an optimized Dijkstra algorithm to reduce the complexity of the calculation of the key path, wherein the key interaction path is the shortest interaction path; finally, respectively marking the frequent item with the highest confidence level in the frequent item set and the key interaction path to a view II, judging whether the required information is obtained from the view I, meeting the conditions and finishing the interaction; otherwise, continuing the interaction until the condition is met.
2. The method of optimizing data exploration according to claim 1, wherein: the method comprises the following specific steps:
step one, defining the interaction of a user:
data exploration requires a user to interact with a view, and the view interacted by the user is set as a view I; according to the method, the interactive process of the user is recorded and analyzed according to the interaction of the user, and the interactive process and the analysis result of the user are marked on another view, so that the user is helped to complete the interaction better, and the view is set as a view II;
N＝{N1，N2，...，Nnn refers to a data state set of a view I after interaction; wherein N isiThe method is characterized in that the data state of a view I is obtained after a user interacts with the view I once; p ═ P1，P2，...，PnP is an interaction path set, which is a set between data states of adjacent views; wherein, PiMeans NiAnd Ni+1User interaction between;
step two, if the required information is obtained from the view one, the interaction is completed; otherwise, carrying out interaction, and then carrying out the third step;
step three, compressing the interaction path set P and the view data state set N:
by traversing the interaction path set P, if there are consecutive identical Pi，Pi+1，...，Pi+nAnd then compare Pi，Pi+1，...，Pi+nView data state N in betweeni+1，Ni+2，...，Ni+n-1View data state NiFor multidimensional data nodes, the similarity comparison is carried out by calculating the Manhattan distance:
wherein, distman(Ni，Ni+1) Represents NiAnd Ni+1The Manhattan distance between, k represents NiHaving k dimensions, NijRepresents NiThe jth dimension of (a); setting a threshold value c 0.15When distman(Ni，Ni+1) C is less than or equal to c, the interaction path Pi+1And view data state Ni+1Is compressed;
step four, grouping of the interaction path sets:
according to PiAnd Pi+1The time interval t between the two groups the interaction path set P, when t < 5s, PiAnd Pi+1Belong to the same group, otherwise Pi+1New packets are formed, thereby obtaining a set of packets G ═ G of interaction paths1，G2，...，GnIn which GiRefers to a group of interaction paths;
step five, mining the frequent item set of the interaction path:
excavating a frequent item set in the group set G of the interactive paths obtained in the step four by adopting an FP-Growth algorithm, wherein the method comprises the following steps: let the number of groups in the interactive path grouping set G be n, and the minimum support degree min of the frequent item setsupportP is equal to p × n, the value range of p is 0.2-0.5, and the length of the frequent item in the frequent item set is 2-5;
step six, extracting a key interaction path:
calculating a key interaction path in the interaction path set according to the interaction path set compressed in the step three by adopting an optimized Dijkstra algorithm, wherein the method comprises the following steps of:
first, an initial starting point is designated as an initial interactive view data state N1Setting two sets S and U, wherein the set S is used for recording the interactive view data state nodes with the shortest paths already obtained, and the U is used for recording the nodes except the nodes in the set S;
then, calculating the current key interaction path PkeycurrThere are two cases according to the difference of the operation:
case one, the interaction is a direct operation on view one, resulting in a new interaction path PiAnd a new interactive view data state NiNew interaction path PiFrom the current interaction view data state Ni-1Pointing to a new Interactive View data State NiNew interactive view data state NiIs added toIn the set U, node NiTo the initial node N1Is the node Ni-1To the initial node N1Plus 1, the distance of (c); from the initial node N1To node NiThe inter-interaction path is a key interaction path;
case two, the interaction is a jump operation between view data states, resulting in a new interaction path PiSearching the shortest distance corresponding to the node after the jump in the set S, wherein the interaction path corresponding to the shortest distance is the key interaction path;
step seven, marking prompt information on the view two:
and respectively labeling the frequent item with the highest confidence level in the frequent item set obtained in the fifth step and the key interaction path obtained in the sixth step on the second view, and returning to the second step.
3. The method of optimizing data exploration according to claim 2, wherein: and in the seventh step, marking the prompt message by using d3 js.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011065504.3A CN112182017B (en) | 2020-09-30 | 2020-09-30 | A method for optimizing data exploration based on user interaction process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011065504.3A CN112182017B (en) | 2020-09-30 | 2020-09-30 | A method for optimizing data exploration based on user interaction process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112182017A true CN112182017A (en) | 2021-01-05 |
| CN112182017B CN112182017B (en) | 2022-06-07 |
Family
ID=73948239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011065504.3A Active CN112182017B (en) | 2020-09-30 | 2020-09-30 | A method for optimizing data exploration based on user interaction process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112182017B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115662158A (en) * | 2022-10-31 | 2023-01-31 | 东南大学 | A traffic overflow-oriented critical path signal control optimization method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8812960B1 (en) * | 2013-10-07 | 2014-08-19 | Palantir Technologies Inc. | Cohort-based presentation of user interaction data |
| US20170039233A1 (en) * | 2015-08-07 | 2017-02-09 | Sap Se | Sankey diagram graphical user interface customization |
| CN108153870A (en) * | 2017-12-25 | 2018-06-12 | 四川长虹电器股份有限公司 | A kind of user access path Forecasting Methodology |
| CN109829008A (en) * | 2018-12-10 | 2019-05-31 | 中科曙光南京研究院有限公司 | A kind of data analysis real time visualized method and system |
| CN110442616A (en) * | 2018-05-02 | 2019-11-12 | 中国科学院声学研究所 | A kind of page access path analysis method and system for big data quantity |
| US20190377818A1 (en) * | 2018-06-11 | 2019-12-12 | The Governing Council Of The University Of Toronto | Data visualization platform for event-based behavior clustering |
| CN110609783A (en) * | 2019-09-24 | 2019-12-24 | 京东数字科技控股有限公司 | Method and device for identifying abnormal behavior user |
-
2020
- 2020-09-30 CN CN202011065504.3A patent/CN112182017B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8812960B1 (en) * | 2013-10-07 | 2014-08-19 | Palantir Technologies Inc. | Cohort-based presentation of user interaction data |
| US20170039233A1 (en) * | 2015-08-07 | 2017-02-09 | Sap Se | Sankey diagram graphical user interface customization |
| CN108153870A (en) * | 2017-12-25 | 2018-06-12 | 四川长虹电器股份有限公司 | A kind of user access path Forecasting Methodology |
| CN110442616A (en) * | 2018-05-02 | 2019-11-12 | 中国科学院声学研究所 | A kind of page access path analysis method and system for big data quantity |
| US20190377818A1 (en) * | 2018-06-11 | 2019-12-12 | The Governing Council Of The University Of Toronto | Data visualization platform for event-based behavior clustering |
| CN109829008A (en) * | 2018-12-10 | 2019-05-31 | 中科曙光南京研究院有限公司 | A kind of data analysis real time visualized method and system |
| CN110609783A (en) * | 2019-09-24 | 2019-12-24 | 京东数字科技控股有限公司 | Method and device for identifying abnormal behavior user |
Non-Patent Citations (4)
| Title |
|---|
| JAEHYUN PARK AND RICHARD BOLAND, JR: "IDENTIFYING A DYNAMIC INTERACTION MODEL: A VIEW FROM THE DESIGNER-USER INTERACTIONS", 《INTERNATIONAL CONFERENCE ON ENGINEERING DESIGN》 * |
| JESU´ S M. ALMENDROS-JIME´ NEZ, LUIS IRIBARNE: "UML Modeling of User and Database", 《THE COMPUTER JOURNAL》 * |
| 丁梦晓，毕强，张晗，李洁: "数字图书馆知识发现系统用户交互优化研究", 《情报资料工作》 * |
| 程时伟，沈哓权，孙凌云，胡屹凛: "多用户眼动跟踪数据的可视化共享与协同交互", 《软件学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115662158A (en) * | 2022-10-31 | 2023-01-31 | 东南大学 | A traffic overflow-oriented critical path signal control optimization method |
| CN115662158B (en) * | 2022-10-31 | 2023-08-29 | 东南大学 | A traffic overflow-oriented critical path signal control optimization method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112182017B (en) | 2022-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zandkarimi et al. | A generic framework for trace clustering in process mining | |
| Gao et al. | Less is more: Efficient 3-D object retrieval with query view selection | |
| Liu et al. | Using consensus clustering for multi-view anomaly detection | |
| CN111382347A (en) | Object feature processing and information pushing method, device and equipment | |
| CN111667881B (en) | Protein function prediction method based on multi-network topology structure | |
| CN101901251B (en) | Cluster Structure Analysis and Identification Method of Complex Network Based on Markov Process Metastability | |
| Paparrizos et al. | A survey on time-series distance measures | |
| Song et al. | Interactive visual pattern search on graph data via graph representation learning | |
| Keyvanpour | A survey on community detection methods based on the nature of social networks | |
| CN112182017A (en) | Method for optimizing data exploration based on user interaction process | |
| Li et al. | Mask-gvae: Blind denoising graphs via partition | |
| CN111177578A (en) | Search method for most influential community around user | |
| Coelho et al. | A multi-objective multipopulation approach for biclustering | |
| CN112733926A (en) | Multi-layer network clustering method based on semi-supervision | |
| CN118965081A (en) | A method for identifying multiple accounts for one person based on online local sensitive hashing algorithm | |
| CN105224687B (en) | A kind of low consumed Apriori methods | |
| CN112765313A (en) | False information detection method based on original text and comment information analysis algorithm | |
| Vandaele et al. | Mining topological structure in graphs through forest representations | |
| Rada et al. | A comparative analysis on prototype-based clustering methods. | |
| Palpanas | Data series management: The next challenge | |
| Huang et al. | Embedding regularized nonnegative matrix factorization for structural reduction in multi-layer networks | |
| Aljibawi et al. | A survey on clustering density based data stream algorithms | |
| CN112925839A (en) | Incremental data set-oriented knowledge discovery method and discovery device | |
| Kamel et al. | MG-join: detecting phenomena and their correlation in high dimensional data streams | |
| Yang et al. | Semi-Supervised Multi-View Ensemble Clustering with Subspaces Extraction and Constraints Propagation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |